On the Feasibility of Internet-Scale Author Identification

By Arvind Narayanan, Hristo S. Paskov, Neil Zhenqiang Gong, John Bethencourt, Emil Stefanov, Eui Chul Richard Shin, Dawn Song. IEEE Symposium on Security and Privacy, 2012

325 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/68930f06c3444d00731fd01b6eb5f5c0b9cc6f1f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Neil Zhenqiang Gong
2. Binghui Wang
3. Jinyuan Jia
4. Yang Zhang
5. Michael Backes
6. Ahmed Salem
7. Le Zhang
8. Bin Liu

Citations in the corpus

• Attribute Inference Attacks in Online Social Networks (2018, methodology): “Narayanan et al. [48] demonstrated a stronger result, i.e., author identity can be deanonymized via writing style analysis.”
• Detecting Hoaxes, Frauds, and Deception in Writing Style Online (2012, unknown): “authors with significant accuracy [17].”
• AttriInfer: Inferring User Attributes in Online Social Networks Using Markov Random Fields (2017, result): “More recent studies [23, 2] demonstrated stronger results, i.”
• Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP (2021, background): “For example, anonymous social media users can be identified based on stylometry and typo patterns (Narayanan et al., 2012).”
• MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples (2019, background): “…than membership inference attacks, many other attacks rely on machine learning classifiers, e.g., attribute inference attacks [11, 17, 28], website fingerprinting attacks [7, 22, 29, 46, 67], side-channel attacks [73], location attacks [5, 45, 52, 72], and author identification attacks [8, 41].”
• You Are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and Behaviors (2016, methodology): “We also tried the confidence estimator called gap statistic [34], in which the confidence score for a targeted user is the difference between the score of the highest ranked attribute value and the score of the second highest ranked one.”